HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Image Super Resolution On Manga109 3X

평가 지표

PSNR

SSIM

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	PSNR	SSIM	Paper Title	Repository
DRLN+	34.94	0.9518	Densely Residual Laplacian Super-Resolution
CPAT	35.66	0.9559	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
ML-CrAIST-Li	34.26	0.9492	ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer
CSNLN	34.45	0.9502	Image Super-Resolution with Cross-Scale Non-Local Attention and Exhaustive Self-Exemplars Mining
HAT	35.84	0.9567	Activating More Pixels in Image Super-Resolution Transformer
CPAT+	35.77	0.9563	Channel-Partitioned Windowed Attention And Frequency Learning for Single Image Super-Resolution	-
HAT_FIR	35.92	-	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
ML-CrAIST	34.42	0.9501	ML-CrAIST: Multi-scale Low-high Frequency Information-based Cross black Attention with Image Super-resolving Transformer
HAT-L	36.02	0.9576	Activating More Pixels in Image Super-Resolution Transformer
HAN+	34.87	0.9509	Single Image Super-Resolution via a Holistic Attention Network
HMA†	36.10	0.9580	HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
PMRN+	34.1	0.9480	Sequential Hierarchical Learning with Distribution Transformation for Image Super-Resolution	-
Hi-IR-L	36.12	0.9588	Hierarchical Information Flow for Generalized Efficient Image Restoration	-
SwinFIR	35.77	0.9563	SwinFIR: Revisiting the SwinIR with Fast Fourier Convolution and Improved Training for Image Super-Resolution
IMDN	33.61	-	Lightweight Image Super-Resolution with Information Multi-distillation Network
SRFBN	34.18	-	Feedback Network for Image Super-Resolution
LFFN-S	32.8	0.9381	Lightweight Feature Fusion Network for Single Image Super-Resolution

0 of 17 row(s) selected.